ClawHub
Back to skill

Security audit

one-plaud-recording-several-differently-formatted-summaries

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Plaud-to-Google Docs/Sheets summarization workflow, with a privacy consideration but no evidence of hidden or unsafe behavior.

Before installing, confirm that the connected Plaud, Google Docs, and Google Sheets accounts are the intended ones, and check sharing/retention settings because meeting or recording summaries can expose sensitive content outside Plaud.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
This workflow processes Plaud recording transcripts and then writes derived summaries plus metadata into Google Docs and Google Sheets, but it does not explicitly warn the user that recordings may contain sensitive personal, business, or regulated information. That omission increases the chance of unintentional disclosure, oversharing to broadly accessible Google assets, or retention of sensitive content in systems with different sharing and compliance controls than the source platform.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.